Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12832
    Prev
    Next
    INDEX
    Explanations

    references to purchasing or acquiring services and products online

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Second-person perspective: "you" followed by modal verbs

    np_acts-logits-general · gemini-2.0-flash

    you to do or get

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.80
    Ārējās
    -0.70
    
    -0.69
     ProtoMessage
    -0.68
    StructEnd
    -0.62
    Lähteet
    -0.60
    <%@
    -0.60
    posedge
    -0.59
     onData
    -0.59
    :✨
    -0.59
    POSITIVE LOGITS
     wish
    0.60
     desire
    0.59
     assume
    0.51
     desejo
    0.50
    desire
    0.48
     favor
    0.48
     select
    0.47
     endwhile
    0.47
     compulsion
    0.47
     presume
    0.47
    Activations Density 0.086%

    No Known Activations